Public
  1. Public

onnxruntime

Public

Commits

Adrian LizarragaGitHub
a8f74e3ec75
Adrian Lizarraga authored and GitHub committed e4c0cb2b9a0
[Quant tool] Do not default to contrib Q/DQ ops for 16-bit (#20376)

### Description
Updates the QDQ quantizer to use ONNX Q/DQ ops for 16-bit quantization
if opset >= 21.

### Motivation and Context
The QDQ quantizer previously set the 'com.microsoft' domain on inserted
Q/DQ ops when the model needed 16-bit support. ONNX 1.16.0 added
int16/uint16 support to the QuantizeLinear and DequantizeLinear
operators, so we can change the default behavior.